Project Report Draft

Motivation

Questions

How does length of maternity leave taken by women in New York City vary according to key socioeconomic characteristics?
How does length of maternity leave differ by zip code? Do these spacial patterns match the distribution of key socioeconomic characteristics?
Is the geographic distribution of average length of maternity leave associated with X, Y, X?

Data

Data Sources

Our primary data source is the NYC Work and Family Leave Survey (WFLS).

The NYC WFLS is a telephone survey conducted in March 2016, which was administered to 1,000 New York City residents who gave birth in 2014. The goal was to understand the availability and accessibility of paid family leave to working parents. The WLFS also sought to describe the role that paid family leave policies play in achieving health equity for parents and children.

NYC zipcodes by neighborhood and borough came from the New York State Department of Health Zipcode Definitions Page.

Variables of interest*

Outcomes

leave_weeks = weeks of maternity leave (paid or unpaid)
paid_leave_weeks = weeks of paid maternity leave
unpaid_leave_weeks = weeks of unpaid maternity leave
postpartum_check = had a postpartum checkup 4-6 weeks after giving birth

Predictors

neighborhood = neighborhood (based on five digit zip code)
race = race of survey respondent
income = family income as percent of the federal poverty level
food_insecurity = concern about having enough food to feed family or receives public assistance in the form of SNAP benefits / food stamps
education = highest grade or year of school completed
partner = co-parenting status (single or co-parent)
job_type = type of employment during pregnancy (government, private company, non-profit, self-employed)

Data Cleaning

Read in data, create new variables, and select key variables for analysis

wfls_df = 
  read_csv("./data/WFLS_2014.csv") %>% 
  mutate(
    recode_el12mns = el12mns*4,
    el11 = as.character(el11),
    leave_type = case_when(
      el11 == '1' ~ "Paid",
      el11 == '2' ~ "Unpaid",
      el11 == '3' ~ "Both",
      el11 == '4' ~ "Did not take time off"),
    leave_weeks = coalesce(recode_el12mns, el12wks),
    leave_weeks = na_if(leave_weeks, 77),
    leave_weeks = na_if(leave_weeks, 99),
    ulw_recode = case_when(
      leave_type == "Unpaid" ~ leave_weeks),
    unpaid_leave_weeks = coalesce(ulw_recode, el13d),
    pct_unpaid = round((unpaid_leave_weeks/leave_weeks)*100),4,
    partner = case_when(
      cp1 == '1' ~ "Co-parent",
      cp1 == '2' ~ "Single Parent"),
    education = case_when(
      d7 == '1' ~ "No high school degree",
      d7 == '2' ~ "No high school degree",
      d7 == '3' ~ "No high school degree",
      d7 == '4' ~ "High school degree/GED",
      d7 == '5' ~ "Some college or technical school",
      d7 == '6' ~ "Four year college or higher"),
    d4_2 = na_if(d4_2, 77),
    d4_2 = na_if(d4_2, 99),
    race = case_when(
      d4_1 == '1' ~ "White",
      d4_1 == '2' ~ "Black/African American",
      d4_1 == '3' ~ "Asian",
      d4_1 == '4' ~ "Native Hawaiian/OPI",
      d4_1 == '5' ~ "American Indian/AN",
      d4_1 == '8' ~ "Other",
      d3 == 1 ~ "Hispanic",
      d4_2 >= 1 ~ "Multiple"),
    job_type = case_when(
      el3 == '1' ~ "Government",
      el3 == '2' ~ "Private",
      el3 == '3' ~ "Non-profit",
      el3 == '4' ~ "Self-employed"), 
    unemploy_reason = el16, 
    unemploy_reason = case_when( 
      el16 == '1' ~ "Fired related to pregnancy or maternity leave", 
      el16 == '2' ~ "Chose to stay-at-home", 
      el16 == '3' ~ "Not enough flexibility", 
      el16 == '4' ~ "No affordable childcare", 
      el16 == '5' ~ "My health issues", 
      el16 == '6' ~ "Baby's health issues", 
      el16 == '7' ~ "Currently a student", 
      el16 == '8' ~ "Can't find work", 
      el16 == '9' ~ "Looking for other jobs", 
      el16 == '10' ~ "other") ,
    bf1_1 = case_when(
      bf1_1 == '1' ~ "Never", 
      bf1_1 == '2' ~ "Less than 1 Week", 
      bf1_1 == '3' ~ "Weeks", 
      bf1_1 == '4' ~ "Months", 
      bf1_1 == '5' ~ "Still breastfeeding", 
      bf1_1 == '77' ~ "don't know", 
      bf1_1 == '99' ~ "refused"), 
    food_insecurity = case_when(
      es2 == 1 ~ 1,
      es1a == 1 ~ 1,
      es1a == 2 ~ 1,
      es1a == 3 ~ 1,
      es2 == 0 ~ 0,
      es1a == 4 ~ 0
    ),
    family_income = case_when(
      es3 == '1' ~ "Less than $16,000",
      es3 == '2' ~ "$16,001 to $20,000",
      es3 == '3' ~ "$20,001 to 40,000",
      es3 == '4' ~ "$20,001 to 40,000",
      es3 == '5' ~ "$20,001 to 40,000",
      es3 == '6' ~ "$20,001 to 40,000",
      es3 == '7' ~ "$40,001 to 60,000",
      es3 == '8' ~ "$40,001 to 60,000",
      es3 == '9' ~ "$40,001 to 60,000",
      es3 == '10' ~ "$60,001 to 85,000",
      es3 == '11' ~ "$60,001 to 85,000",
      es3 == '12' ~ "More than $85,000"
    ),
      postpartum_check = case_when(
      pph1 == '1' ~ "yes", 
      pph1 == '2' ~ "no"), 
    zipcode = fixd2) %>% 
  select("ph1":"el1", "el9", "el11", "el13a":"el17f", "ih1", "mh4", "es1a": "es3", "SAMP_WEIGHT", "POP_WEIGHT", "leave_type":"pct_unpaid", "partner":"zipcode", "postpartum_check")

Save cleaned data set

write.csv(wfls_df, "./data/cleaned_wfls.csv")

Merge data sets

cleaned_wfls = 
  read_csv("./data/cleaned_wfls.csv")

zipcodes =
  read_xlsx("./data/zip_codes.xlsx") %>% 
  mutate(zipcode = as.character(zipcode))

merged_wfls = 
  left_join(cleaned_wfls, zipcodes, by = "zipcode")

write.csv(merged_wfls, "./data/merged_wfls.csv")

Plots

Maternity Leave by Race

race = 
  merged_wfls %>% 
  drop_na(race) %>% 
  drop_na(leave_weeks) %>% 
 mutate(race = fct_reorder(race, leave_weeks)) %>% 
  ggplot(aes(x = race, y = leave_weeks, fill = race, alpha = 0.9)) + 
    geom_boxplot() + 
  theme(axis.text.x = element_text(angle = 60, vjust = 0.5, hjust = 1), legend.position = "none") +
  labs(
    title = "Weeks of maternity leave by race",
    x = "Race",
    y = "Weeks of leave"
  )

ggplotly(race)

1a) Unpaid Leave by Race

unpaid = 
  merged_wfls %>% 
  drop_na(race) %>% 
  drop_na(unpaid_leave_weeks) %>% 
  mutate(race = fct_reorder(race, unpaid_leave_weeks)) %>% 
  ggplot(aes(x = race, y = unpaid_leave_weeks, fill = race, alpha = 0.9)) + 
    geom_boxplot() + 
  theme(axis.text.x = element_text(angle = 60, vjust = 0.5, hjust = 1), legend.position = "none") +
  labs(
    title = "Unpaid maternity leave by race",
    x = "Race",
    y = "Unpaid Weeks of leave"
  )

ggplotly(unpaid)

Length of maternity leave by co-parenting status

parent = 
  merged_wfls %>% 
  drop_na(partner) %>% 
  drop_na(leave_weeks) %>%
 ggplot(aes(x = partner, y = leave_weeks, fill = partner)) +
  geom_boxplot() +
  labs(
    title = "Weeks of maternity leave by co-parenting status",
    x = "Co-parenting status",
    y = "Weeks of leave"
  )
ggplotly(parent)

3a) income, food insecurity, and unpaid leave weeks

unpaid = 
merged_wfls %>% 
drop_na(family_income) %>% 
drop_na(unpaid_leave_weeks) %>% 
mutate(food_insecurity = as.character(food_insecurity), 
       food_insecurity = case_when(
         food_insecurity == '0' ~ "no", 
         food_insecurity == '1' ~ "yes"), 
       family_income = fct_reorder(family_income, es3)) %>% 
   ggplot(aes(x = family_income, y = unpaid_leave_weeks, color = food_insecurity)) + 
  geom_point() + 
theme(axis.text.x = element_text(angle = 60, vjust = 0.5, hjust = 1)) +
  labs(
    title = "Unpaid maternity leave by income",
    x = "Family Income",
    y = "Weeks of unpaidleave"
  )

ggplotly(unpaid)

3b) income, food insecurity, and leave weeks

income = 
merged_wfls %>% 
drop_na(family_income) %>% 
drop_na(leave_weeks) %>% 
mutate(food_insecurity = as.character(food_insecurity), 
       food_insecurity = case_when(
         food_insecurity == '0' ~ "no", 
         food_insecurity == '1' ~ "yes"), 
       family_income = fct_reorder(family_income, es3)) %>% 
   ggplot(aes(x = family_income, y = leave_weeks, color = food_insecurity)) + 
  geom_point() + 
theme(axis.text.x = element_text(angle = 60, vjust = 0.5, hjust = 1)) +
  labs(
    title = "Paid leave by income",
    x = "Family Income",
    y = "Weeks of leave"
  )

ggplotly(income)

Factors Affecting Return to work

unemploy = 
merged_wfls %>% 
  drop_na(unemploy_reason) %>% 
  ggplot(aes(x = unemploy_reason, fill = race)) + geom_bar(position = "dodge") + 
  theme(axis.text.x = element_text(angle = 60, vjust = 0.5, hjust = 1)) + 
  labs(
    title = "Reasons for Unemployment",
    x = "Reason",
    y = "Count") 

ggplotly(unemploy)

4b return to work by education

unemploy2 = 
merged_wfls %>% 
  drop_na(unemploy_reason) %>% 
  ggplot(aes(x = unemploy_reason, fill = education)) + geom_bar(position = "dodge") + 
  theme(axis.text.x = element_text(angle = 60, vjust = 0.5, hjust = 1)) + 
  labs(
    title = "Reasons for Unemployment",
    x = "Reason",
    y = "Count") 

ggplotly(unemploy2)

PostPartum checkup and family income

check = 
merged_wfls %>% 
  drop_na(postpartum_check) %>% 
  ggplot(aes(x = postpartum_check, fill = family_income)) + geom_bar(position = "dodge") + 
  theme(axis.text.x = element_text(angle = 60, vjust = 0.5, hjust = 1)) + 
  labs(
    title = "Postpartum Check",
    x = "Postpartum Check status",
    y = "Count") 

ggplotly(check)

Neighborhood and leave

neighborhood = 
  merged_wfls %>% 
  drop_na(race) %>% 
  drop_na(leave_weeks) %>% 
 mutate(race = fct_reorder(neighborhood, leave_weeks)) %>% 
  ggplot(aes(x = neighborhood, y = leave_weeks, fill = race)) + 
    geom_violin() + 
  theme(axis.text.x = element_text(angle = 60, vjust = 0.5, hjust = 1), legend.position = "none") +
  labs(
    title = "Weeks of maternity leave by neighborhood",
    x = "neighborhood",
    y = "Weeks of leave"
  )

ggplotly(neighborhood)

Akanksha Nalatwad, Amanda Warnock, Meghan Bellerose, Karina Myers

Visualizations and analyses performed using R (v3.6.1) and RStudio (v1.2.1335).
Additional interactivity added using plotly (v4.9.0) and Shiny (v1.3.2).

2020